<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<identifier>8JMKD3MGPBW34M/3JRK52L</identifier>
		<repository>sid.inpe.br/sibgrapi/2015/07.13.14.36</repository>
		<lastupdate>2015:07.13.14.36.06 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2015/07.13.14.36.06</metadatarepository>
		<metadatalastupdate>2016:06.03.21.18.36 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2015}</metadatalastupdate>
		<citationkey>MotaDiaSanVieAra:2015:TeClHu</citationkey>
		<title>Tensor Clustering for Human Action Recognition</title>
		<format>On-line</format>
		<year>2015</year>
		<numberoffiles>1</numberoffiles>
		<size>929 KiB</size>
		<author>Mota, Virginia Fernandes,</author>
		<author>Dias, Gabriel Dutra,</author>
		<author>Santos, Wisney Tadeu dos,</author>
		<author>Vieira, Marcelo Bernardes,</author>
		<author>Araújo, Arnaldo de Albuquerque,</author>
		<affiliation>NPDI/DCC/UFMG and COLTEC/UFMG</affiliation>
		<affiliation>COLTEC/UFMG</affiliation>
		<affiliation>COLTEC/UFMG</affiliation>
		<affiliation>GCG/DCC/UFJF</affiliation>
		<affiliation>NPDI/DCC/UFMG</affiliation>
		<editor>Rios, Ricardo Araujo,</editor>
		<editor>Paiva, Afonso,</editor>
		<e-mailaddress>virginiafernandesmota@gmail.com</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)</conferencename>
		<conferencelocation>Salvador</conferencelocation>
		<date>Aug. 26-29, 2015</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Work in Progress</tertiarytype>
		<transferableflag>1</transferableflag>
		<keywords>orientation tensor, tensor clustering, bag-of-features, human action recognition.</keywords>
		<abstract>In this work, we present a new technique called Bag- of-tensors. This research aims to create a new method for video description based on tensors which takes into account the nature of the tensor and its anisotropic properties. Therefore, the Bag-of- tensors is composed by three main steps: Feature extraction with tensor creation, coding based on tensor clustering and aggregated pooling. For the task of human action recognition, we used the KTH dataset. Our experiments show that this technique is promising and interesting to be further explored.</abstract>
		<language>en</language>
		<targetfile>paper_id_13_wip2015.pdf</targetfile>
		<usergroup>administrator</usergroup>
		<usergroup>virginiafernandesmota@gmail.com</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPBW34M/3K24PF8</nexthigherunit>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2015/07.13.14.36</url>
	</metadata>
</metadatalist>